All modelsCalculate what your real prompts cost on Gemma 4 31B
Gemma 4 31B
Google model, released 2 Apr 2026.
$0.1
per 1M input tokens
$0.34
per 1M output tokens
$0.1
per 1M cached-read tokens
Price history
input $/1M output $/1M7 Jul 2026 → 21 Aug 2026
Specifications
- Lab
- Released
- 2 Apr 2026
- Context window
- 262k tokens
- Max output
- 262k tokens
- Input modalities
- image, text, video
- Output modalities
- text
- Knowledge cutoff
- —
- Open source
- No
Benchmarks
| Benchmark | Category | Score | As of |
|---|---|---|---|
| LMArena (Chatbot Arena) | coding | 1455 (1439.7–1470.3) | 12 Aug 2026 |
| LMArena (Chatbot Arena) | overall | 1441.7 (1434.2–1449.3) | 12 Aug 2026 |
LMArena (Chatbot Arena) data © their authors, CC-BY-4.0
Frequently asked questions
How much does Gemma 4 31B cost?
Gemma 4 31B costs $0.1 per 1M input tokens and $0.34 per 1M output tokens (list price, updated every 6 hours).
What is Gemma 4 31B's context window?
Gemma 4 31B supports a 262k-token context window with up to 262k output tokens.
Related models
Gemini 3.7 Flash
Google · $0.375/$1.88 per 1M
Gemini 3.6 Flash
Google · $0.75/$3.75 per 1M
Gemini 3.5 Flash Lite
Google · $0.3/$2.50 per 1M
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Google · $0.25/$1.50 per 1M
Nano Banana 2 (Gemini 3.1 Flash Image)
Google · $0.5/$3.00 per 1M
Nano Banana Pro (Gemini 3 Pro Image)
Google · $2.00/$12.00 per 1M